hue

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and inspect arbitrary public brand sites and user-provided URLs (see "Brand Name" and the "URL" analysis steps requiring WebSearch, WebFetch and mcp__chrome-devtools__* to open and scrape pages, screenshots, and subpages), which clearly ingests untrusted third‑party web content that can influence the agent's subsequent design decisions and tool use.